Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1978 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.2162. Min Range: -4.2162

Max Act: 4.2162. Min Act: -0.1700

Data Index: 4841470 (Open Web Text)

Max Activating Token Index: 366

Text #1

Max Range: 4.2162. Min Range: -4.2162

Max Act: 4.2013. Min Act: -0.1700

Data Index: 8072598 (Open Web Text)

Max Activating Token Index: 41

Text #2

Max Range: 4.2162. Min Range: -4.2162

Max Act: 4.1281. Min Act: -0.1700

Data Index: 2054563 (Open Web Text)

Max Activating Token Index: 119

Text #3

Max Range: 4.2162. Min Range: -4.2162

Max Act: 4.1812. Min Act: -0.1700

Data Index: 8546700 (Open Web Text)

Max Activating Token Index: 333

Text #4

Max Range: 4.2162. Min Range: -4.2162

Max Act: 4.1319. Min Act: -0.1700

Data Index: 3214568 (Open Web Text)

Max Activating Token Index: 77

Text #5

Max Range: 4.2162. Min Range: -4.2162

Max Act: 4.1596. Min Act: -0.1700

Data Index: 1673147 (Open Web Text)

Max Activating Token Index: 341

Text #6

Max Range: 4.2162. Min Range: -4.2162

Max Act: 4.1169. Min Act: -0.1700

Data Index: 5542738 (Open Web Text)

Max Activating Token Index: 1020

Text #7

Max Range: 4.2162. Min Range: -4.2162

Max Act: 4.1152. Min Act: -0.1700

Data Index: 4406835 (Open Web Text)

Max Activating Token Index: 629

Text #8

Max Range: 4.2162. Min Range: -4.2162

Max Act: 4.1165. Min Act: -0.1700

Data Index: 8136441 (Open Web Text)

Max Activating Token Index: 344

Text #9

Max Range: 4.2162. Min Range: -4.2162

Max Act: 4.0693. Min Act: -0.1700

Data Index: 2921986 (Open Web Text)

Max Activating Token Index: 397

Text #10

Max Range: 4.2162. Min Range: -4.2162

Max Act: 4.0352. Min Act: -0.1700

Data Index: 4114457 (Open Web Text)

Max Activating Token Index: 937

Text #11

Max Range: 4.2162. Min Range: -4.2162

Max Act: 4.0551. Min Act: -0.1700

Data Index: 2891028 (Open Web Text)

Max Activating Token Index: 572

Text #12

Max Range: 4.2162. Min Range: -4.2162

Max Act: 4.0701. Min Act: -0.1700

Data Index: 3338000 (Open Web Text)

Max Activating Token Index: 63

Text #13

Max Range: 4.2162. Min Range: -4.2162

Max Act: 4.0644. Min Act: -0.1700

Data Index: 4694506 (Open Web Text)

Max Activating Token Index: 250

Text #14

Max Range: 4.2162. Min Range: -4.2162

Max Act: 4.0729. Min Act: -0.1700

Data Index: 1702299 (Open Web Text)

Max Activating Token Index: 452

Text #15

Max Range: 4.2162. Min Range: -4.2162

Max Act: 4.0547. Min Act: -0.1700

Data Index: 569077 (Open Web Text)

Max Activating Token Index: 478

Text #16

Max Range: 4.2162. Min Range: -4.2162

Max Act: 4.0666. Min Act: -0.1700

Data Index: 1671965 (Open Web Text)

Max Activating Token Index: 850

Text #17

Max Range: 4.2162. Min Range: -4.2162

Max Act: 4.0374. Min Act: -0.1700

Data Index: 1777157 (Open Web Text)

Max Activating Token Index: 254

Text #18

Max Range: 4.2162. Min Range: -4.2162

Max Act: 4.0172. Min Act: -0.1700

Data Index: 5685417 (Open Web Text)

Max Activating Token Index: 971

Text #19

Max Range: 4.2162. Min Range: -4.2162

Max Act: 4.0429. Min Act: -0.1700

Data Index: 1844157 (Open Web Text)

Max Activating Token Index: 513